Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2011 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2977. Min Act: -0.1700

Data Index: 3679901 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.3043. Min Act: -0.1700

Data Index: 2118990 (Open Web Text)

Max Activating Token Index: 461

Text #2

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2978. Min Act: -0.1700

Data Index: 3594128 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2733. Min Act: -0.1700

Data Index: 4678865 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2766. Min Act: -0.1700

Data Index: 7912210 (Open Web Text)

Max Activating Token Index: 826

Text #5

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2547. Min Act: -0.1700

Data Index: 7513612 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2334. Min Act: -0.1700

Data Index: 4088689 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2284. Min Act: -0.1700

Data Index: 3438230 (Open Web Text)

Max Activating Token Index: 305

Text #8

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2354. Min Act: -0.1700

Data Index: 132571 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2499. Min Act: -0.1700

Data Index: 3535256 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2003. Min Act: -0.1700

Data Index: 721452 (Open Web Text)

Max Activating Token Index: 765

Text #11

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2149. Min Act: -0.1700

Data Index: 8217800 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.1928. Min Act: -0.1700

Data Index: 133275 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.1947. Min Act: -0.1700

Data Index: 2140019 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2017. Min Act: -0.1700

Data Index: 6484298 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2051. Min Act: -0.1700

Data Index: 5936648 (Open Web Text)

Max Activating Token Index: 760

Text #16

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.2094. Min Act: -0.1700

Data Index: 5054482 (Open Web Text)

Max Activating Token Index: 105

Text #17

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.1950. Min Act: -0.1700

Data Index: 3711662 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.1540. Min Act: -0.1700

Data Index: 984215 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.3043. Min Range: -3.3043

Max Act: 3.1970. Min Act: -0.1700

Data Index: 2489455 (Open Web Text)

Max Activating Token Index: 970